Update app.py

app.py

@@ -1,24 +1,47 @@
-# app.py
 from fastapi import FastAPI, UploadFile, File
 from fastapi.responses import JSONResponse
+from fastapi.middleware.cors import CORSMiddleware
 from keras.models import load_model
 from huggingface_hub import hf_hub_download
 from PIL import Image
 import numpy as np
-import uvicorn
+import gradio as gr
 
-# 🔹 Download model from Hugging Face Hub
+# -------------------------------
+# FASTAPI SETUP
+# -------------------------------
+app = FastAPI(title="Cancer Detection API")
+
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+# -------------------------------
+# MODEL LOADING
+# -------------------------------
 MODEL_PATH = hf_hub_download(
     repo_id="aadityaramrame/blood-cell-cancer-detector",
     filename="cancer_classifier.h5"
 )
-
-# 🔹 Load the trained model
 model = load_model(MODEL_PATH)
 
-# 🔹 Initialize FastAPI app
-app = FastAPI(title="Cancer Detection API")
+# Class mapping
+CLASSES = [
+    "platelet",
+    "monocyte",
+    "lymphocyte",
+    "erythroblast",
+    "eosinophil",
+    "basophil"
+]
 
+# -------------------------------
+# FASTAPI ENDPOINTS
+# -------------------------------
 @app.get("/")
 async def root():
     return {"message": "🚀 Cancer Detection API is live!"}
@@ -26,26 +49,14 @@ async def root():
 @app.post("/predict")
 async def predict(file: UploadFile = File(...)):
     try:
-        # Load and preprocess image
         image = Image.open(file.file).convert("RGB").resize((224, 224))
         img_array = np.expand_dims(np.array(image) / 255.0, axis=0)
 
-        # Predict
         prediction = model.predict(img_array)
         predicted_class = int(np.argmax(prediction))
         confidence = float(np.max(prediction))
 
-        # 🔹 Map class index to cell type
-        classes = [
-            "platelet",
-            "monocyte",
-            "lymphocyte",
-            "erythroblast",
-            "eosinophil",
-             "basophil"
-        ]
-
-        label = classes[predicted_class]
+        label = CLASSES[predicted_class]
 
         return JSONResponse(
             content={
@@ -54,11 +65,33 @@ async def predict(file: UploadFile = File(...)):
                 "raw_index": predicted_class
             }
         )
-
     except Exception as e:
         return JSONResponse(content={"error": str(e)}, status_code=500)
 
-# 🔹 This line is CRUCIAL for Hugging Face Spaces
-# It ensures the FastAPI app is visible when the Space starts
-if __name__ == "__main__":
-    uvicorn.run("app:app", host="0.0.0.0", port=7860)
+# -------------------------------
+# GRADIO FRONTEND
+# -------------------------------
+def classify_cancer(image):
+    try:
+        image = image.convert("RGB").resize((224, 224))
+        img_array = np.expand_dims(np.array(image) / 255.0, axis=0)
+        prediction = model.predict(img_array)
+        predicted_class = int(np.argmax(prediction))
+        confidence = float(np.max(prediction))
+        label = CLASSES[predicted_class]
+        return {label: confidence}
+    except Exception as e:
+        return {"Error": str(e)}
+
+gradio_interface = gr.Interface(
+    fn=classify_cancer,
+    inputs=gr.Image(type="pil", label="Upload Blood Cell Image"),
+    outputs=gr.Label(num_top_classes=3, label="Predicted Cell Type"),
+    title="🧫 Blood Cell Cancer Detection",
+    description="Upload a blood cell image to predict the cell type using a trained CNN model.",
+    theme="soft"
+)
+
+# Mount Gradio on FastAPI
+app = gr.mount_gradio_app(app, gradio_interface, path="/")
+